© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55706
    Prev
    Next
    INDEX
    Explanations

    many times

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ung
    0.47
    G
    0.45
     नामों
    0.42
     अनावश्यक
    0.42
     Namen
    0.42
    example
    0.41
    igrams
    0.41
    ine
    0.41
    ug
    0.41
    onas
    0.41
    POSITIVE LOGITS
     somew
    0.45
     financials
    0.45
     जानना
    0.45
    ۔
    0.45
     барои
    0.44
     reorgan
    0.44
    ကြား
    0.43
     devenir
    0.43
     kanggo
    0.43
     fürs
    0.42
    Activations Density 0.000%

    No Known Activations